Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quotes and statements from people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antino
    -0.16
     if
    -0.15
     otherwise
    -0.15
     why
    -0.15
    owler
    -0.15
    moz
    -0.15
    instead
    -0.14
     then
    -0.14
    achen
    -0.14
     you
    -0.14
    POSITIVE LOGITS
    Congratulations
    0.19
     Congratulations
    0.18
     thru
    0.17
    having
    0.17
     alike
    0.17
     having
    0.17
     Through
    0.16
     Having
    0.16
     Working
    0.15
    Through
    0.15
    Act Density 0.038%

    No Known Activations